Data Analytics and Machine Learning for Integrated Corridor Management

Machine learning is an exciting topic with a myriad of applications. However, most textbooks are targeted towards computer science students. This, however, creates a complication for scientists across the physical sciences that also want to understand the main concepts of machine learning and look ahead to applica- tions and advancements in their fields.This textbook bridges this gap, providing an introduction to the mathematical foundations for the main algorithms used in machine learning for those from the physical sciences, without a formal background in computer science. It demon- strates how machine learning can be used to solve problems in physics and engineering, targeting senior undergraduate and graduate students in physics and electrical engineering, alongside advanced researchers.All codes are available on the author's website: C•Lab (nau.edu)They are also available on GitHub: https://github.com/StxGuy/MachineLearningKey Features: Includes detailed algorithms. Supplemented by codes in Julia: a high-performing language and one that is easy to read for those in the natural sciences. All algorithms are presented with a good mathematical background. Cover Half Title Title Page Copyright Page Dedication Contents List of Figures List of Tables Authors Chapter 1: Introduction 1.1. General Concepts of Traffic Management 1.1.1. Traditional Approach to Traffic Management 1.1.2. Integrated Corridor Operations 1.1.3. Congestion and Incidents 1.1.4. Performance Metrics 1.1.5. Response and Optimization Strategies 1.1.6. Traffic Control Systems 1.2. Data Driven Decision Support Systems 1.2.1. Data Analytics and Machine Learning for Traffic Operations 1.2.2. Integration of ICM systems, Data, and Algorithms 1.3. Outline of the book Chapter 2: Traffic Engineering and Operations Background 2.1. Signal Timing Fundamentals 2.1.1. Space Time Diagram 2.1.2. Traffic Signal Modes 2.1.3. Signal Coordination Challenges 2.1.4. Signal Priority and Preemption 2.2. Limited Access Facility Operations 2.2.1. Traffic Incident and Response 2.2.2. Special operating modes: normal, evacuation, should use, priority/preemption 2.2.3. Traffic Control Systems 2.3. Advanced Traveler Management Strategies 2.3.1. Managed Lanes 2.3.2. Ramp Metering 2.3.3. Dynamic Lane Control 2.3.4. Variable Speed Limit 2.3.5. Speed Harmonization 2.3.6. Diversion Routing 2.3.7. Signal Control 2.3.8. Bus Bridging 2.4. Integrated Corridor Management Policies and Constraints 2.4.1. Public Safety 2.4.2. Engineering oversight 2.4.3. Safe Timing patterns 2.4.4. Data Requirements 2.4.5. Cross-jurisdictional change management 2.5. Conclusions Chapter 3: Integrated Corridor Management System 3.1. Introduction 3.2. System 3.2.1. Data Management Subsystem 3.2.2. Decision Support System 3.2.3. User Interface Subsystem 3.3. Traffic Incident Response 3.3.1. Limited-Access Facilities 3.3.2. Arterial Facilities 3.4. Periodic Signal Timing Optimization 3.5. Optimize network for recurring congestion 3.6. Mitigate impacts from non-recurring congestion 3.7. Conclusions Chapter 4: Traffic Data Modalities 4.1. Fixed Point Detection 4.1.1. Loop Detectors 4.1.2. Microwave Detectors 4.1.3. Video and LiDAR Detectors 4.2. Vehicle Probe Detection 4.3. Vehicle Trajectory Data 4.4. Incident Data 4.4.1. Incident Detection 4.4.2. Operational Response 4.5. Other Datasets 4.5.1. Third-Party Traffic Conditions Data 4.5.2. Multimode Data 4.6. Automated Trafic Signal Performance Measures 4.7. Corridor Performance Data 4.8. Traffic Data Horizons 4.8.1. Long Range Planning 4.8.2. Medium Scale Planning 4.8.3. Active Operations 4.9. Data Quality 4.9.1. Accuracy 4.9.2. Availability and Coverage 4.9.3. Validation 4.9.4. Data Format: Machine Accessibility and Readability 4.9.5. Data Latency 4.10. Conclusions Chapter 5: Data Mining and Machine Learning 5.1. Clustering 5.2. Outlier Detection 5.3. Neural Networks 5.3.1. Feed Forward Neural Networks 5.3.2. Recurrent Neural Networks 5.4. Transformers 5.5. Conclusions Chapter 6: Traffic Simulation Frameworks for Data Generation 6.1. Traffic Simulation Frameworks 6.1.1. VISSIM 6.1.2. SUMO 6.1.3. CARLA 6.2. Simulation Calibration 6.2.1. Flow Calibration 6.2.2. Overspeeding Calibration 6.3. Dataset Generation 6.3.1. Intersection Configuration 6.3.2. Input Traffic Generation 6.3.3. Parallelization 6.4. Conclusions Chapter 7: Intersection Detector Diagnostics 7.1. Problem Definition 7.2. Feature Extraction 7.2.1. Signal Timing Pattern Identification and Clustering 7.2.2. Feature Detection 7.3. Data Mining Approach 7.3.1. Inference from a Single Cluster 7.3.2. Inference from Multiple Clusters 7.3.3. Classifying Detectors 7.4. Neural Network Approach 7.5. Verification 7.5.1. Case Study 1 7.5.2. Case Study 2 7.6. Conclusions Chapter 8: Intersection Performance 8.1. Unsupervised Data Summarization 8.1.1. Performance Measures 8.1.2. Compression and Dimensionality Reduction 8.2. Nonlinear Dimensionality Reduction and Clustering 8.2.1. Dimensionality Reduction and Clustering Approaches 8.2.2. Ordering Clusters by Performance 8.3. Change Detection 8.4. Conclusion Chapter 9: Interruption Detection 9.1. Related Work 9.2. Data Preprocessing 9.3. Labelling Interruptions 9.4. Detecting Interruptions 9.5. Conclusions Chapter 10: Estimating Turning Movement Counts 10.1. Related Work 10.1.1. Flow-based Methods 10.1.2. Neural Network Based Approaches 10.1.3. Other Approaches 10.2. Machine Learning Models for TMC Prediction 10.3. Conclusions Chapter 11: Coordinating Corridors 11.1. Intersection Level MoE Modeling 11.1.1. Descriptive Modeling 11.1.2. Experimental results 11.2. Clustering and Spatiotemporal Corridor Decomposition 11.2.1. Hour of Day Clustering 11.2.2. Day of Week Clustering 11.2.3. Spatial Decomposition of Corridors 11.3. Results and Case Studies 11.4. Related Work 11.5. Conclusion Chapter 12: Modeling Input Output behavior of Intersection 12.1. Related Work 12.2. Proposed Models 12.2.1. Stop-Bar-to-Exit Waveform Prediction Model 12.2.2. Inflow Waveform Reconstruction Model 12.2.3. Exit-to-Downstream Waveform Prediction Model 12.2.4. Stop-Bar-Advance Waveform Model 12.3. Proposed Neural Network Architectures 12.4. Experimental Results 12.5. Conclusions Chapter 13: Modeling measures of effectiveness for intersection performance 13.1. Related Work 13.2. Proposed Framework 13.2.1. Spatial Graph Convolution 13.2.2. Encoder Decoder with Temporal Attention 13.2.3. Overall Network 13.3. Experimental Results 13.4. Case Study 13.5. Conclusions Chapter 14: Signal Timing Optimization 14.1. Mathematical Modeling-based Methods 14.1.1. Minimum Cost Flow Algorithm 14.1.2. Arterial Traffic Signal Optimization 14.2. Machine Learning-based Methods 14.3. Quantum Annealing-based Methods Chapter 15: Visualization of Traffic Data 15.1. Functional Architecture & Key Modules 15.1.1. Ranking and Classification 15.1.2. Clustering 15.1.3. Change Detection 15.1.4. Interruption Detection 15.2. Visualization 15.3. System and Performance Appendix A: Acknowledgements for Materials References Index In an era defined by rapid urbanization and ever-increasing mobility demands, effective transportation management is paramount. This book takes readers on a journey through the intricate web of contemporary transportation systems, offering unparalleled insights into the strategies, technologies, and methodologies shaping the movement of people and goods in urban landscapes. From the fundamental principles of traffic signal dynamics to the cutting-edge applications of machine learning, each chapter of this comprehensive guide unveils essential aspects of modern transportation management systems. Chapter by chapter, readers are immersed in the complexities of traffic signal coordination, corridor management, data-driven decision-making, and the integration of advanced technologies. Closing with chapters on modeling measures of effectiveness and computational signal timing optimization, the guide equips readers with the knowledge and tools needed to navigate the complexities of modern transportation management systems. With insights into traffic data visualization and operational performance measures, this book empowers traffic engineers and administrators to design 21st-century signal policies that optimize mobility, enhance safety, and shape the future of urban transportation.